A user classification apparatus and method using a keystroke pattern based on a user posture are provided. A user classification method using a keystroke pattern may include receiving keystroke data from a user, extracting feature information corresponding to a unique pattern of the user using the received keystroke data, comparing the extracted feature information to a pattern of a keystroke profile for each posture of the user pre-generated through training, and determining whether currently input keystroke data is data of a trained user based on a result of the comparing.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A user classification method using a keystroke pattern in a mobile device, the method comprising: receiving keystroke data from a user when the user performs authentication of an application included in the mobile device; extracting feature information including data for a posture performed by the user when the user performs keystroke and data for a keystroke pattern using the received keystroke data; classifying the posture of the user by comparing the feature information to posture feature information, the posture feature information having been generated based on postures performed by general users, the postures including a walking posture, a sitting posture, and a lying-down posture; selecting a keystroke profile that corresponds to the classified posture of the user; comparing the feature information to a pattern of the selected keystroke profile; determining whether the user is a pre-trained user based on a result of the comparing; and authenticating the user to use the application based on a result of the determining.
2. The method of claim 1 , wherein the keystroke data is generated when the user presses a key, and the keystroke data comprises time information of when a key is pressed and released and sensor information collected from an accelerometer sensor, a gyroscope sensor, and a proximity sensor during a time corresponding to the time information.
3. The method of claim 1 , wherein the posture feature information has been generated independently from the pre-trained user.
4. A keystroke pattern training method comprising: receiving keystroke data from a user when the user performs authentication of an application included in a mobile device; extracting feature information including data for a posture performed by the user when the user performs keystroke and data for a keystroke pattern using the received keystroke data; classifying the posture of the user by comparing the feature information to posture feature information, the posture feature information having been generated based on postures performed by general users, the postures including a walking posture, a sitting posture, and a lying-down posture; and training the keystroke pattern for the classified posture of the user using the feature information.
5. The method of claim 4 , further comprising storing the trained keystroke pattern for the classified posture in a form of a keystroke profile.
6. The method of claim 4 , wherein the posture feature information has been generated based on one or more of walking posture, sitting posture, and lying down posture.
7. The method of claim 4 , wherein the keystroke data is generated when the user presses a key, and the keystroke data comprises time information of when a key is pressed and released and sensor information collected during a time corresponding to the time information.
8. The method of claim 4 , wherein the posture feature information has been generated independently from the user.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 9, 2016
December 25, 2018
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.